perf tools: Add time out to force stop proc map processing

System wide sampling like 'perf top' or 'perf record -a' read all
threads /proc/xxx/maps before sampling. If there are any threads which
generating a keeping growing huge maps, perf will do infinite loop
during synthesizing. Nothing will be sampled.

This patch fixes this issue by adding per-thread timeout to force stop
this kind of endless proc map processing.

PERF_RECORD_MISC_PROC_MAP_PARSE_TIME_OUT is introduced to indicate that
the mmap record are truncated by time out. User will get warning
notification when truncated mmap records are detected.

Reported-by: Ying Huang <ying.huang@intel.com>
Signed-off-by: Kan Liang <kan.liang@intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ying Huang <ying.huang@intel.com>
Link: http://lkml.kernel.org/r/1434549071-25611-1-git-send-email-kan.liang@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This commit is contained in:
Kan Liang 2015-06-17 09:51:10 -04:00 committed by Arnaldo Carvalho de Melo
parent c05676c062
commit 930e6fcd2b
4 changed files with 34 additions and 0 deletions

View File

@ -565,6 +565,10 @@ struct perf_event_mmap_page {
#define PERF_RECORD_MISC_GUEST_KERNEL (4 << 0)
#define PERF_RECORD_MISC_GUEST_USER (5 << 0)
/*
* Indicates that /proc/PID/maps parsing are truncated by time out.
*/
#define PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT (1 << 12)
/*
* PERF_RECORD_MISC_MMAP_DATA and PERF_RECORD_MISC_COMM_EXEC are used on
* different events so can reuse the same bit position.

View File

@ -213,6 +213,8 @@ static int perf_event__synthesize_fork(struct perf_tool *tool,
return 0;
}
#define PROC_MAP_PARSE_TIMEOUT (500 * 1000000ULL)
int perf_event__synthesize_mmap_events(struct perf_tool *tool,
union perf_event *event,
pid_t pid, pid_t tgid,
@ -222,6 +224,8 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
{
char filename[PATH_MAX];
FILE *fp;
unsigned long long t;
bool truncation = false;
int rc = 0;
if (machine__is_default_guest(machine))
@ -240,6 +244,7 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
}
event->header.type = PERF_RECORD_MMAP2;
t = rdclock();
while (1) {
char bf[BUFSIZ];
@ -253,6 +258,12 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
if (fgets(bf, sizeof(bf), fp) == NULL)
break;
if ((rdclock() - t) > PROC_MAP_PARSE_TIMEOUT) {
pr_warning("Reading %s time out.\n", filename);
truncation = true;
goto out;
}
/* ensure null termination since stack will be reused. */
strcpy(execname, "");
@ -301,6 +312,10 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
event->header.misc |= PERF_RECORD_MISC_MMAP_DATA;
}
out:
if (truncation)
event->header.misc |= PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT;
if (!strcmp(execname, ""))
strcpy(execname, anonstr);
@ -319,6 +334,9 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
rc = -1;
break;
}
if (truncation)
break;
}
fclose(fp);

View File

@ -265,6 +265,7 @@ struct events_stats {
u32 nr_unknown_id;
u32 nr_unprocessable_samples;
u32 nr_auxtrace_errors[PERF_AUXTRACE_ERROR_MAX];
u32 nr_proc_map_timeout;
};
struct attr_event {

View File

@ -1064,6 +1064,8 @@ static int machines__deliver_event(struct machines *machines,
case PERF_RECORD_MMAP:
return tool->mmap(tool, event, sample, machine);
case PERF_RECORD_MMAP2:
if (event->header.misc & PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT)
++evlist->stats.nr_proc_map_timeout;
return tool->mmap2(tool, event, sample, machine);
case PERF_RECORD_COMM:
return tool->comm(tool, event, sample, machine);
@ -1360,6 +1362,15 @@ static void perf_session__warn_about_errors(const struct perf_session *session)
ui__warning("%u out of order events recorded.\n", oe->nr_unordered_events);
events_stats__auxtrace_error_warn(stats);
if (stats->nr_proc_map_timeout != 0) {
ui__warning("%d map information files for pre-existing threads were\n"
"not processed, if there are samples for addresses they\n"
"will not be resolved, you may find out which are these\n"
"threads by running with -v and redirecting the output\n"
"to a file.\n",
stats->nr_proc_map_timeout);
}
}
static int perf_session__flush_thread_stack(struct thread *thread,